Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    references to specific politicians, particularly mentions of Barack Obama

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    MJ
    -0.76
    ãĥ¼ãĥĨ
    -0.74
    driving
    -0.66
    NP
    -0.66
    Els
    -0.65
    ãĥ¼ãĥĨãĤ£
    -0.65
    PsyNetMessage
    -0.64
    ãĤ¯
    -0.63
    eon
    -0.62
    coins
    -0.62
    POSITIVE LOGITS
     vetoed
    0.91
     toured
    0.88
     appoint
    0.88
     congratulated
    0.87
     visited
    0.85
     Jr
    0.83
     hailed
    0.82
     appointed
    0.82
     condol
    0.81
     greets
    0.81
    Act Density 0.137%

    No Known Activations